Sam Altman-led OpenAI is working on a groundbreaking reasoning technology for its large language models (LLMs), codenamed Strawberry, Reuters reported on Friday. Internal company documents and sources familiar with the matter reveal that this technology aims to significantly enhance the reasoning capabilities of OpenAI’s AI models.
According to the report, Strawberry is a closely guarded secret within the organization. It was initially known as Q* and has been regarded as a major breakthrough within the company.
However, OpenAI has demonstrated Q* to some of its staff, showcasing the LLMs’ ability to tackle complex science and mathematics questions that are currently beyond the capabilities of commercially available models.
The internal document details a project involving Strawberry models, which are designed to enable the company’s AI to not only generate answers to queries but also plan ahead sufficiently to navigate the internet autonomously and reliably to perform what OpenAI calls “deep research,” according to the source.
What is Strawberry?
Strawberry is reportedly a specialised method of processing an AI model after it has been pre-trained on extensive datasets. This involves a unique approach to ‘post-training’ OpenAI’s generative AI models, or adapting them to enhance their performance in specific ways even after they have been trained on generalised data.
OpenAI intends to utilise Strawberry for performing long-horizon tasks (LHT), which require an AI model to plan ahead and execute a series of actions over an extended period. Specifically, OpenAI aims for its models to use these capabilities to conduct research by autonomously browsing the web with the support of a ‘computer using agent’ (CUA) that can take action based on its findings.
“3.6 Crore Indians visited in a single day, choosing us as India’s undisputed platform for General Election Results. Explore the latest updates.”
OpenAI’s development of Strawberry represents a significant leap in the field of AI, with the potential to drastically improve the reasoning capabilities of its models. By enabling autonomous, deep research capabilities, Strawberry could set a new standard for AI applications.
Stay tuned for more updates on OpenAI’s innovative projects and breakthroughs in AI technology. Sign up for our newsletter to receive the latest news directly to your inbox.
